diff --git a/AddedAnnotations.py b/AddedAnnotations.py index 2f5f3f2..c1ee04d 100644 --- a/AddedAnnotations.py +++ b/AddedAnnotations.py @@ -132,7 +132,6 @@ def run(filename): Example: python AddedAnnotations.py -w '[{"/path/to/working/folder"}]' -f '[{"/path/to/EMDB/header/files/folder"}]' - -p '[{"/path/to/PDBe/files/folder"}]' --uniprot --CPX --component --model --weight --pmc --GO --interpro --pfam --pbdekb --cath --scop --scop2 --scop2B --rfam """ @@ -142,7 +141,6 @@ def run(filename): parser.add_argument("-h", "--help", action="help", help="Show this help message and exit.") parser.add_argument('-w', '--workDir', type=Path, help="Main working directory path .") parser.add_argument('-f', '--headerDir', type=Path, help="Directory path to the EMDB version 3.0 header files.") - parser.add_argument('-p', '--PDBeDir', type=Path, help="Directory path to the PDBe Complex portal mapping files.") parser.add_argument('-t', '--threads', type=int, default=4, help="Number of threads.") parser.add_argument('--json', type=Path, help="Path to release json file.") parser.add_argument("--all", type=bool, nargs='?', const=True, default=False, help="Fetch all external resources.") diff --git a/XMLParser.py b/XMLParser.py index ccc860e..27b3f0e 100644 --- a/XMLParser.py +++ b/XMLParser.py @@ -103,7 +103,7 @@ def read_xml(self): supramolecule = Supramolecule(self.emdb_id, complex_id) supramolecule.id = f"supra_{complex_id}" #TODO: Is this supra_ id used anywhere? supramolecule.type = "supra" #TODO: Where is it being used? - complex_name = complex_tag.find('name').text + complex_name = complex_tag.find('name').text.replace('\t', ' ').strip() supramolecule.name = f"{complex_name}_{complex_id}" self.supramolecules.append(supramolecule) @@ -119,7 +119,7 @@ def read_xml(self): sample_id = protein_tag.attrib['macromolecule_id'] protein = Protein(self.emdb_id, sample_id) protein.pdb = self.models - protein.sample_name = protein_tag.find('name').text + protein.sample_name = protein_tag.find('name').text.replace('\t', ' ').strip() if sample_id in protein_cpx: protein.sample_complexes = list(protein_cpx[sample_id]) if protein_tag.find('number_of_copies') is not None: